© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64143
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     possibly
    -0.29
    å¼ºåĽ½
    -0.28
    èµŀèµı
    -0.27
    çĥĤ
    -0.25
    åĤĻ
    -0.24
    è½»è½»åľ°
    -0.24
    该éĻ¢
    -0.24
    CAA
    -0.24
     admittedly
    -0.24
    æ·±åĬłå·¥
    -0.24
    POSITIVE LOGITS
    åı¸
    0.27
    sky
    0.26
     Secrets
    0.26
    utivo
    0.26
    antee
    0.26
     Parl
    0.24
    -rate
    0.24
    ansom
    0.24
     Secret
    0.24
    ossip
    0.23
    Activations Density 1.166%

    No Known Activations

    This feature has no known activations.